def getXLeastSimilarIndex(term, terms_to_match, terms_to_ignore, amt): least_similar_term_indexes = [] for a in range(amt): lowest_term = 99999999 term_index = 0 for t in range(len(terms_to_match)): if dt.checkIfInArray(terms_to_ignore, t) is False: s = getSimilarity(term, terms_to_match[t]) if s < lowest_term and dt.checkIfInArray(least_similar_term_indexes, t) is False: lowest_term = s term_index = t least_similar_term_indexes.append(term_index) return least_similar_term_indexes
def getXMostSimilarIndex(term, terms_to_match, terms_to_ignore, amt): most_similar_term_indexes = [] for a in range(amt): highest_term = 0 term_index = 0 for t in range(len(terms_to_match)): if dt.checkIfInArray(terms_to_ignore, t) is False: s = getSimilarity(term, terms_to_match[t]) if s > highest_term and dt.checkIfInArray(most_similar_term_indexes, t) is False: highest_term = s term_index = t most_similar_term_indexes.append(term_index) return most_similar_term_indexes
def getXMostSimilarIndex(term, terms_to_match, terms_to_ignore, amt): most_similar_term_indexes = [] for a in range(amt): highest_term = 0 term_index = 0 for t in range(len(terms_to_match)): if dt.checkIfInArray(terms_to_ignore, t) is False: s = getSimilarity(term, terms_to_match[t]) if s > highest_term and dt.checkIfInArray( most_similar_term_indexes, t) is False: highest_term = s term_index = t most_similar_term_indexes.append(term_index) return most_similar_term_indexes
def getXLeastSimilarIndex(term, terms_to_match, terms_to_ignore, amt): least_similar_term_indexes = [] for a in range(amt): lowest_term = 99999999 term_index = 0 for t in range(len(terms_to_match)): if dt.checkIfInArray(terms_to_ignore, t) is False: s = getSimilarity(term, terms_to_match[t]) if s < lowest_term and dt.checkIfInArray( least_similar_term_indexes, t) is False: lowest_term = s term_index = t least_similar_term_indexes.append(term_index) return least_similar_term_indexes
def getNextClusterTerm(cluster_terms, terms_to_match, terms_to_ignore, amt): min_value = 999999999999999 min_index = 0 for t in range(len(terms_to_match)): max_value = 0 if dt.checkIfInArray(terms_to_ignore, t) is False: for c in range(len(cluster_terms)): s = getSimilarity(cluster_terms[c], terms_to_match[t]) if s > max_value: max_value = s if max_value < min_value: min_value = max_value min_index = t return min_index